Zhang Fengying, Liu Yan, Ma Weijie, Zhao Shengming, Chen Jin, Gu Zhichun
Department of Evidence-Based Medicine and Clinical Epidemiology, West China Hospital, Sichuan University, Chengdu 610041, China.
Department of Clinical Pharmacy, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200092, China.
J Pers Med. 2022 Apr 29;12(5):717. doi: 10.3390/jpm12050717.
: This study aimed to systematically assess the characteristics and risk of bias of previous studies that have investigated nonlinear machine learning algorithms for warfarin dose prediction. We systematically searched PubMed, Embase, Cochrane Library, Chinese National Knowledge Infrastructure (CNKI), China Biology Medicine (CBM), China Science and Technology Journal Database (VIP), and Wanfang Database up to March 2022. We assessed the general characteristics of the included studies with respect to the participants, predictors, model development, and model evaluation. The methodological quality of the studies was determined, and the risk of bias was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST). From a total of 8996 studies, 23 were assessed in this study, of which 23 (100%) were retrospective, and 11 studies focused on the Asian population. The most common demographic and clinical predictors were age (21/23, 91%), weight (17/23, 74%), height (12/23, 52%), and amiodarone combination (11/23, 48%), while CYP2C9 (14/23, 61%), VKORC1 (14/23, 61%), and CYP4F2 (5/23, 22%) were the most common genetic predictors. Of the included studies, the MAE ranged from 1.47 to 10.86 mg/week in model development studies, from 2.42 to 5.18 mg/week in model development with external validation (same data) studies, from 12.07 to 17.59 mg/week in model development with external validation (another data) studies, and from 4.40 to 4.84 mg/week in model external validation studies. All studies were evaluated as having a high risk of bias. Factors contributing to the risk of bias include inappropriate exclusion of participants (10/23, 43%), small sample size (15/23, 65%), poor handling of missing data (20/23, 87%), and incorrect method of selecting predictors (8/23, 35%). Most studies on nonlinear-machine-learning-based warfarin prediction models show poor methodological quality and have a high risk of bias. The analysis domain is the major contributor to the overall high risk of bias. External validity and model reproducibility are lacking in most studies. Future studies should focus on external validity, diminish risk of bias, and enhance real-world clinical relevance.
本研究旨在系统评估既往调查用于华法林剂量预测的非线性机器学习算法的研究的特征和偏倚风险。我们系统检索了截至2022年3月的PubMed、Embase、Cochrane图书馆、中国知网（CNKI）、中国生物医学文献数据库（CBM）、维普中文科技期刊数据库（VIP）和万方数据库。我们评估了纳入研究在参与者、预测因素、模型开发和模型评估方面的一般特征。确定了研究的方法学质量，并使用预测模型偏倚风险评估工具（PROBAST）评估偏倚风险。在总共8996项研究中，本研究评估了23项，其中23项（100%）为回顾性研究，11项研究聚焦于亚洲人群。最常见的人口统计学和临床预测因素是年龄（21/23，91%）、体重（17/23，74%）、身高（12/23，52%）和胺碘酮联合用药（11/23，48%），而细胞色素P450 2C9（CYP2C9，14/23，61%）、维生素K环氧化物还原酶复合体1（VKORC1，14/23，61%）和细胞色素P450 4F2（CYP4F2，5/23，22%）是最常见的基因预测因素。在纳入的研究中，模型开发研究的平均绝对误差（MAE）范围为1.47至10.86mg/周，外部验证（相同数据）的模型开发研究为2.42至5.18mg/周，外部验证（另一组数据）的模型开发研究为12.07至17.59mg/周，模型外部验证研究为4.40至4.84mg/周。所有研究均被评估为具有较高的偏倚风险。导致偏倚风险的因素包括不适当排除参与者（10/23，43%）、样本量小（15/23，65%）、缺失数据处理不当（20/23，87%）以及预测因素选择方法错误（8/23，35%）。大多数基于非线性机器学习的华法林预测模型研究显示方法学质量较差且具有较高的偏倚风险。分析领域是总体高偏倚风险的主要促成因素。大多数研究缺乏外部有效性和模型可重复性。未来的研究应关注外部有效性，降低偏倚风险，并增强与现实世界临床的相关性。
